How AI is powering Sam’s Club’s Christmas range

When a member of one of the 600 Sam’s Clubs in the US wants a fresh pumpkin pie to serve this holiday season, Vinod Bidarkoppa, SVP and chief technology officer at Sam’s Club, wants to make sure it’s on the shelf and ready to go. to go.

Unlike mass-market retailers such as Walmart, the parent company of Sam’s Club, the main strategy for a member-only warehouse chain is to satisfy and retain members. That’s why Sam’s Club has steadily stepped up its efforts in the field of artificial intelligence (AI), based on connected intelligence. Since joining the company in February 2020, Bidarkoppa said his team has been working hard to figure out how to get the right range of products to the right stores at the right time, especially during peak seasons.

“With accurate AI predictions, we sold enough pies last year to cover the length of 450 football fields, while staying ahead of customer demand and reducing food waste,” Bidarkoppa told VentureBeat. “If we really made our members happy and every member who wanted a pumpkin pie got it, then that’s a win for us.”

Sam’s Club needs to understand demand and stock

The journey of Sam’s Club pumpkin pies begins with determining how many pies members will buy in the 600 clubs – and thus how many should be ordered from suppliers and shipped to stores.

“We are doing a machine learning [ML] based on forecasts that look at a number of variables, including local weather conditions, holiday dates and shelf life, and come up with an unbiased, unlimited demand forecast,” he said. “Then, suppliers replenish pumpkin pies at distribution centers, where machine learning also exists to help in planning the most efficient way to ship all those pumpkin pies to the 600 clubs.”

After they arrive in stores, the pumpkin pies—which arrive half-frozen and need to be prepared for sale—must be stocked on the shelves. But how many are needed to meet member demand without the leftovers going to waste? AI and ML also play a role there.

“If you have too much stock, a lot is lost,” he said. “But if you’re under-produced, you have a disappointed member who says, ‘What’s the holiday without a pumpkin pie?’

The company’s Fresh Sales app uses AI to predict — in some cases, hourly — how many pies or other products to fill, based on ML predictions generated for each item in the club.

“This system takes into account the minimum level of presentation – how much inventory I want to have in that club at any given time,” he said. “So it almost always feels like it’s full and we don’t disappoint members.”

Last week, Sam’s Club unveiled its latest computer vision-based ML tool, a self-contained floor scrubber that does indeed clean the floors, but also has a mounted camera that scans and captures all items on store shelves twice a day. The scrubber then sends “hot item” alerts to the backroom so employees can prioritize the receipt of items most at risk of being sold out.

“We have patented models around object detection with an accuracy of about 90% and coverage of the entire clubroom,” said Bidarkoppa.

Once a truckload of pumpkin pies arrives from the distribution center, Sam’s Club’s ClubIQ tool determines the order employees need to get the pies and other items from the truck. The system also analyzes the historical sales behavior of items for upcoming holiday events and tells employees which items to put on the floor first based on that item’s popularity – down to the club level.

Connecting the Sam’s Club AI Ecosystem

“This is an ecosystem that exists in a machine-driven model,” explains Birdarkoppa. “Ultimately, the goal is really to please our members, but all of this is the AI ​​behind it.”

This connected AI and ML-powered ecosystem also continues to learn over time.

“It doesn’t stop at the data signals we pick up,” he said. “We feed it back into the model and these become learning systems. So the more we learn from the signals, the better the models become and the better the outcome for both our employees and our members.”

Club employees, he emphasizes, love the inventory information and item recognition technology.

“Instead of having to figure out all these details manually, the machine helps them very precisely,” he said. “They love the fact that there are things that help our members instead of having to do unnecessary administrative manual tasks – today we are north of 15% of the tasks that are automatically handled by this technology, and imagine that on our scale.”

Sam’s Club wants to build on AI success

Birdarkoppa says Sam’s Club plans to build on its AI efforts — which clearly go beyond pumpkin pies.

“Whether it’s planning, buying, scheduling, relocating or selling all of these core retail processes, we will continue to be committed to machine learning,” he said. “There’s a long list of things on my to-do list and I’m really excited about what we can do with this technology, both for our members and our employees.”

As a membership-focused organization, Birdarkoppa reiterated the company’s need for a member-centric lens for all of its processes and tasks.

“That flows through the technology stack and how we work within the tech organization,” he said. So are AI-driven tools — one of the objective features in any Sam’s Club algorithm, for example, is how it will affect member retention and growth.

“Ultimately, we’re working on making our members happy,” he said.